L3 Empathy Response Strategy: converts text into a deterministic response strategy (approach, tone temperature, pacing, focus points, avoid-list) for AI companions and conversational agents. Deterministic table lookup, no LLM, ~20ms; privacy-first. Not a medical or therapeutic tool.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well: it discloses deterministic table lookup, no LLM involvement, ~20ms latency, privacy-first behavior, and non-medical scope. These are meaningful behavioral traits beyond what a schema or annotation would typically convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tightly packed sentences front-load the core purpose and then add high-value behavioral and performance details. No filler or redundant repetition of the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter tool with an output schema present, the description covers the core transformation, output aspects, performance characteristics, privacy stance, and a key limitation. Nothing critical is missing for an agent to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage for the only parameter, but the description clarifies that 'text' is the input to be converted into a response strategy. It doesn't specify length/format constraints, but for a single obvious text parameter, this is adequate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('converts') and names the resource ('text into a deterministic response strategy') with concrete output elements (approach, tone temperature, pacing, focus points, avoid-list). It clearly distinguishes this from likely siblings like analyze_text or somatic_decode by framing it as an empathy-response strategy tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states the intended context ('for AI companions and conversational agents') and adds an explicit exclusion ('Not a medical or therapeutic tool'). It does not name alternative tools or provide if-then routing guidance, but the target use case is clear enough for an agent to select it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool is clearly pinned to a distinct stage and input: raw text emotion analysis, avatar parameter driving, empathy response strategy, and somatic body-sensation decoding. Even though analyze_text and somatic_decode share emotion-output dimensions, the text vs. body-sensation input boundary plus the explicit L1/L4 labels make misselection unlikely.
The names use snake_case but mix conventions: analyze_text and generate_avatar_params are verb_noun, while empathy_hint is noun_noun and somatic_decode reads as adjective+verb. This is readable but less predictable than a uniform verb_noun pattern.
Four tools map cleanly onto the four advertised affect-processing levels (L1-L4) with no redundant duplicates. The count feels deliberately scoped for a focused affective-computing API.
The surface covers the core lifecycle from text/body input through affect analysis, avatar parameters, and empathy strategies, so the main workflows are present. Minor gaps exist around cross-chaining outputs (e.g., a somatic decode cannot directly feed the avatar or empathy tools) and there is no batch/status endpoint, but these are workable.